# StemGen: A music generation model that listens Source: [StemGen: A music generation model that listens]() Collection index: [llms.txt]() Data updated: 2025-10-26T02:12:32.787Z Authors: Julian D. Parker, Janne Spijkervet, Katerina Kosta, Furkan Yesiler, Boris Kuznetsov, Ju-Chiang Wang, Matt Avent, Jitong Chen, Duc Le Published: 2023-12-14T08:09:20.000Z ## Abstract End-to-end generation of musical audio using deep learning techniques has seen an explosion of activity recently. However, most models concentrate on generating fully mixed music in response to abstract conditioning information. In this work, we present an alternative paradigm for producing music generation models that can listen and respond to musical context. We describe how such a model can be constructed using a non-autoregressive, transformer-based model architecture and present a number of novel architectural and sampling improvements. We train the described architecture on both an open-source and a proprietary dataset. We evaluate the produced models using standard quality metrics and a new approach based on music information retrieval descriptors. The resulting model reaches the audio quality of state-of-the-art text-conditioned models, as well as exhibiting strong musical coherence with its context. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multi-track music generation on Slakh2100 (test)](): Multi-track music generation; Slakh2100 (test); FAD: 4.3. ## Original sources and implementation [Original paper]() [PDF]()